Merge branch 'tip/rtmutex' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into core/locking

*git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace tip/rtmutex:
   rtmutex: Simplify PI algorithm and make highest prio task get lock

10 files changed, 321 insertions, 335 deletions

diff --git a/kernel/futex.c b/kernel/futex.c
index b766d28accd6..64c38115c7b6 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1556,10 +1556,10 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 
         /*
          * We are here either because we stole the rtmutex from the
-         * pending owner or we are the pending owner which failed to
-         * get the rtmutex. We have to replace the pending owner TID
-         * in the user space variable. This must be atomic as we have
-         * to preserve the owner died bit here.
+         * previous highest priority waiter or we are the highest priority
+         * waiter but failed to get the rtmutex the first time.
+         * We have to replace the newowner TID in the user space variable.
+         * This must be atomic as we have to preserve the owner died bit here.
          *
          * Note: We write the user space value _before_ changing the pi_state
          * because we can fault here. Imagine swapped out pages or a fork
@@ -1608,8 +1608,8 @@ retry:
 
         /*
          * To handle the page fault we need to drop the hash bucket
-         * lock here. That gives the other task (either the pending
-         * owner itself or the task which stole the rtmutex) the
+         * lock here. That gives the other task (either the highest priority
+         * waiter itself or the task which stole the rtmutex) the
          * chance to try the fixup of the pi_state. So once we are
          * back from handling the fault we need to check the pi_state
          * after reacquiring the hash bucket lock and before trying to
@@ -1685,18 +1685,20 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
                 /*
                  * pi_state is incorrect, some other task did a lock steal and
                  * we returned due to timeout or signal without taking the
-                 * rt_mutex. Too late. We can access the rt_mutex_owner without
-                 * locking, as the other task is now blocked on the hash bucket
-                 * lock. Fix the state up.
+                 * rt_mutex. Too late.
                  */
+                raw_spin_lock(&q->pi_state->pi_mutex.wait_lock);
                 owner = rt_mutex_owner(&q->pi_state->pi_mutex);
+                if (!owner)
+                        owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
+                raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock);
                 ret = fixup_pi_state_owner(uaddr, q, owner);
                 goto out;
         }
 
         /*
          * Paranoia check. If we did not take the lock, then we should not be
-         * the owner, nor the pending owner, of the rt_mutex.
+         * the owner of the rt_mutex.
          */
         if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
                 printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
diff --git a/kernel/params.c b/kernel/params.c
index 08107d181758..0da1411222b9 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -719,9 +719,7 @@ void destroy_params(const struct kernel_param *params, unsigned num)
                         params[i].ops->free(params[i].arg);
 }
 
-static void __init kernel_add_sysfs_param(const char *name,
-                                          struct kernel_param *kparam,
-                                          unsigned int name_skip)
+static struct module_kobject * __init locate_module_kobject(const char *name)
 {
         struct module_kobject *mk;
         struct kobject *kobj;
@@ -729,10 +727,7 @@ static void __init kernel_add_sysfs_param(const char *name,
 
         kobj = kset_find_obj(module_kset, name);
         if (kobj) {
-                /* We already have one.  Remove params so we can add more. */
                 mk = to_module_kobject(kobj);
-                /* We need to remove it before adding parameters. */
-                sysfs_remove_group(&mk->kobj, &mk->mp->grp);
         } else {
                 mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
                 BUG_ON(!mk);
@@ -743,15 +738,36 @@ static void __init kernel_add_sysfs_param(const char *name,
                                            "%s", name);
                 if (err) {
                         kobject_put(&mk->kobj);
-                        printk(KERN_ERR "Module '%s' failed add to sysfs, "
-                               "error number %d\n", name, err);
-                        printk(KERN_ERR "The system will be unstable now.\n");
-                        return;
+                        printk(KERN_ERR
+                                "Module '%s' failed add to sysfs, error number %d\n",
+                                name, err);
+                        printk(KERN_ERR
+                                "The system will be unstable now.\n");
+                        return NULL;
                 }
-                /* So that exit path is even. */
+
+                /* So that we hold reference in both cases. */
                 kobject_get(&mk->kobj);
         }
 
+        return mk;
+}
+
+static void __init kernel_add_sysfs_param(const char *name,
+                                          struct kernel_param *kparam,
+                                          unsigned int name_skip)
+{
+        struct module_kobject *mk;
+        int err;
+
+        mk = locate_module_kobject(name);
+        if (!mk)
+                return;
+
+        /* We need to remove old parameters before adding more. */
+        if (mk->mp)
+                sysfs_remove_group(&mk->kobj, &mk->mp->grp);
+
         /* These should not fail at boot. */
         err = add_sysfs_param(mk, kparam, kparam->name + name_skip);
         BUG_ON(err);
@@ -796,6 +812,32 @@ static void __init param_sysfs_builtin(void)
         }
 }
 
+ssize_t __modver_version_show(struct module_attribute *mattr,
+                              struct module *mod, char *buf)
+{
+        struct module_version_attribute *vattr =
+                container_of(mattr, struct module_version_attribute, mattr);
+
+        return sprintf(buf, "%s\n", vattr->version);
+}
+
+extern struct module_version_attribute __start___modver[], __stop___modver[];
+
+static void __init version_sysfs_builtin(void)
+{
+        const struct module_version_attribute *vattr;
+        struct module_kobject *mk;
+        int err;
+
+        for (vattr = __start___modver; vattr < __stop___modver; vattr++) {
+                mk = locate_module_kobject(vattr->module_name);
+                if (mk) {
+                        err = sysfs_create_file(&mk->kobj, &vattr->mattr.attr);
+                        kobject_uevent(&mk->kobj, KOBJ_ADD);
+                        kobject_put(&mk->kobj);
+                }
+        }
+}
 
 /* module-related sysfs stuff */
 
@@ -875,6 +917,7 @@ static int __init param_sysfs_init(void)
         }
         module_sysfs_initialized = 1;
 
+        version_sysfs_builtin();
         param_sysfs_builtin();
 
         return 0;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 84522c796987..126a302c481c 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2201,13 +2201,6 @@ find_lively_task_by_vpid(pid_t vpid)
         if (!task)
                 return ERR_PTR(-ESRCH);
 
-        /*
-         * Can't attach events to a dying task.
-         */
-        err = -ESRCH;
-        if (task->flags & PF_EXITING)
-                goto errout;
-
         /* Reuse ptrace permission checks for now. */
         err = -EACCES;
         if (!ptrace_may_access(task, PTRACE_MODE_READ))
@@ -2268,14 +2261,27 @@ retry:
 
                 get_ctx(ctx);
 
-                if (cmpxchg(&task->perf_event_ctxp[ctxn], NULL, ctx)) {
-                        /*
-                         * We raced with some other task; use
-                         * the context they set.
-                         */
+                err = 0;
+                mutex_lock(&task->perf_event_mutex);
+                /*
+                 * If it has already passed perf_event_exit_task().
+                 * we must see PF_EXITING, it takes this mutex too.
+                 */
+                if (task->flags & PF_EXITING)
+                        err = -ESRCH;
+                else if (task->perf_event_ctxp[ctxn])
+                        err = -EAGAIN;
+                else
+                        rcu_assign_pointer(task->perf_event_ctxp[ctxn], ctx);
+                mutex_unlock(&task->perf_event_mutex);
+
+                if (unlikely(err)) {
                         put_task_struct(task);
                         kfree(ctx);
-                        goto retry;
+
+                        if (err == -EAGAIN)
+                                goto retry;
+                        goto errout;
                 }
         }
 
@@ -5374,6 +5380,8 @@ free_dev:
         goto out;
 }
 
+static struct lock_class_key cpuctx_mutex;
+
 int perf_pmu_register(struct pmu *pmu, char *name, int type)
 {
         int cpu, ret;
@@ -5422,6 +5430,7 @@ skip_type:
 
                 cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
                 __perf_event_init_context(&cpuctx->ctx);
+                lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
                 cpuctx->ctx.type = cpu_context;
                 cpuctx->ctx.pmu = pmu;
                 cpuctx->jiffies_interval = 1;
@@ -6127,7 +6136,7 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn)
          * scheduled, so we are now safe from rescheduling changing
          * our context.
          */
-        child_ctx = child->perf_event_ctxp[ctxn];
+        child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]);
         task_ctx_sched_out(child_ctx, EVENT_ALL);
 
         /*
@@ -6440,11 +6449,6 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
         unsigned long flags;
         int ret = 0;
 
-        child->perf_event_ctxp[ctxn] = NULL;
-
-        mutex_init(&child->perf_event_mutex);
-        INIT_LIST_HEAD(&child->perf_event_list);
-
         if (likely(!parent->perf_event_ctxp[ctxn]))
                 return 0;
 
@@ -6533,6 +6537,10 @@ int perf_event_init_task(struct task_struct *child)
 {
         int ctxn, ret;
 
+        memset(child->perf_event_ctxp, 0, sizeof(child->perf_event_ctxp));
+        mutex_init(&child->perf_event_mutex);
+        INIT_LIST_HEAD(&child->perf_event_list);
+
         for_each_task_context_nr(ctxn) {
                 ret = perf_event_init_context(child, ctxn);
                 if (ret)
diff --git a/kernel/printk.c b/kernel/printk.c
index 53d9a9ec88e6..2ddbdc73aade 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -97,7 +97,7 @@ static int console_locked, console_suspended;
 /*
  * logbuf_lock protects log_buf, log_start, log_end, con_start and logged_chars
  * It is also used in interesting ways to provide interlocking in
- * release_console_sem().
+ * console_unlock();.
  */
 static DEFINE_SPINLOCK(logbuf_lock);
 
@@ -501,7 +501,7 @@ static void _call_console_drivers(unsigned start,
 /*
  * Call the console drivers, asking them to write out
  * log_buf[start] to log_buf[end - 1].
- * The console_sem must be held.
+ * The console_lock must be held.
  */
 static void call_console_drivers(unsigned start, unsigned end)
 {
@@ -604,11 +604,11 @@ static int have_callable_console(void)
  *
  * This is printk().  It can be called from any context.  We want it to work.
  *
- * We try to grab the console_sem.  If we succeed, it's easy - we log the output and
+ * We try to grab the console_lock.  If we succeed, it's easy - we log the output and
  * call the console drivers.  If we fail to get the semaphore we place the output
  * into the log buffer and return.  The current holder of the console_sem will
- * notice the new output in release_console_sem() and will send it to the
- * consoles before releasing the semaphore.
+ * notice the new output in console_unlock(); and will send it to the
+ * consoles before releasing the lock.
  *
  * One effect of this deferred printing is that code which calls printk() and
  * then changes console_loglevel may break. This is because console_loglevel
@@ -659,19 +659,19 @@ static inline int can_use_console(unsigned int cpu)
 /*
  * Try to get console ownership to actually show the kernel
  * messages from a 'printk'. Return true (and with the
- * console_semaphore held, and 'console_locked' set) if it
+ * console_lock held, and 'console_locked' set) if it
  * is successful, false otherwise.
  *
  * This gets called with the 'logbuf_lock' spinlock held and
  * interrupts disabled. It should return with 'lockbuf_lock'
  * released but interrupts still disabled.
  */
-static int acquire_console_semaphore_for_printk(unsigned int cpu)
+static int console_trylock_for_printk(unsigned int cpu)
         __releases(&logbuf_lock)
 {
         int retval = 0;
 
-        if (!try_acquire_console_sem()) {
+        if (console_trylock()) {
                 retval = 1;
 
                 /*
@@ -827,12 +827,12 @@ asmlinkage int vprintk(const char *fmt, va_list args)
          * actual magic (print out buffers, wake up klogd,
          * etc). 
          *
-         * The acquire_console_semaphore_for_printk() function
+         * The console_trylock_for_printk() function
          * will release 'logbuf_lock' regardless of whether it
          * actually gets the semaphore or not.
          */
-        if (acquire_console_semaphore_for_printk(this_cpu))
-                release_console_sem();
+        if (console_trylock_for_printk(this_cpu))
+                console_unlock();
 
         lockdep_on();
 out_restore_irqs:
@@ -993,7 +993,7 @@ void suspend_console(void)
         if (!console_suspend_enabled)
                 return;
         printk("Suspending console(s) (use no_console_suspend to debug)\n");
-        acquire_console_sem();
+        console_lock();
         console_suspended = 1;
         up(&console_sem);
 }
@@ -1004,7 +1004,7 @@ void resume_console(void)
                 return;
         down(&console_sem);
         console_suspended = 0;
-        release_console_sem();
+        console_unlock();
 }
 
 /**
@@ -1027,21 +1027,21 @@ static int __cpuinit console_cpu_notify(struct notifier_block *self,
         case CPU_DYING:
         case CPU_DOWN_FAILED:
         case CPU_UP_CANCELED:
-                acquire_console_sem();
-                release_console_sem();
+                console_lock();
+                console_unlock();
         }
         return NOTIFY_OK;
 }
 
 /**
- * acquire_console_sem - lock the console system for exclusive use.
+ * console_lock - lock the console system for exclusive use.
  *
- * Acquires a semaphore which guarantees that the caller has
+ * Acquires a lock which guarantees that the caller has
  * exclusive access to the console system and the console_drivers list.
  *
  * Can sleep, returns nothing.
  */
-void acquire_console_sem(void)
+void console_lock(void)
 {
         BUG_ON(in_interrupt());
         down(&console_sem);
@@ -1050,21 +1050,29 @@ void acquire_console_sem(void)
         console_locked = 1;
         console_may_schedule = 1;
 }
-EXPORT_SYMBOL(acquire_console_sem);
+EXPORT_SYMBOL(console_lock);
 
-int try_acquire_console_sem(void)
+/**
+ * console_trylock - try to lock the console system for exclusive use.
+ *
+ * Tried to acquire a lock which guarantees that the caller has
+ * exclusive access to the console system and the console_drivers list.
+ *
+ * returns 1 on success, and 0 on failure to acquire the lock.
+ */
+int console_trylock(void)
 {
         if (down_trylock(&console_sem))
-                return -1;
+                return 0;
         if (console_suspended) {
                 up(&console_sem);
-                return -1;
+                return 0;
         }
         console_locked = 1;
         console_may_schedule = 0;
-        return 0;
+        return 1;
 }
-EXPORT_SYMBOL(try_acquire_console_sem);
+EXPORT_SYMBOL(console_trylock);
 
 int is_console_locked(void)
 {
@@ -1095,20 +1103,20 @@ void wake_up_klogd(void)
 }
 
 /**
- * release_console_sem - unlock the console system
+ * console_unlock - unlock the console system
  *
- * Releases the semaphore which the caller holds on the console system
+ * Releases the console_lock which the caller holds on the console system
  * and the console driver list.
  *
- * While the semaphore was held, console output may have been buffered
- * by printk().  If this is the case, release_console_sem() emits
- * the output prior to releasing the semaphore.
+ * While the console_lock was held, console output may have been buffered
+ * by printk().  If this is the case, console_unlock(); emits
+ * the output prior to releasing the lock.
  *
  * If there is output waiting for klogd, we wake it up.
  *
- * release_console_sem() may be called from any context.
+ * console_unlock(); may be called from any context.
  */
-void release_console_sem(void)
+void console_unlock(void)
 {
         unsigned long flags;
         unsigned _con_start, _log_end;
@@ -1141,7 +1149,7 @@ void release_console_sem(void)
         if (wake_klogd)
                 wake_up_klogd();
 }
-EXPORT_SYMBOL(release_console_sem);
+EXPORT_SYMBOL(console_unlock);
 
 /**
  * console_conditional_schedule - yield the CPU if required
@@ -1150,7 +1158,7 @@ EXPORT_SYMBOL(release_console_sem);
  * if this CPU should yield the CPU to another task, do
  * so here.
  *
- * Must be called within acquire_console_sem().
+ * Must be called within console_lock();.
  */
 void __sched console_conditional_schedule(void)
 {
@@ -1171,14 +1179,14 @@ void console_unblank(void)
                 if (down_trylock(&console_sem) != 0)
                         return;
         } else
-                acquire_console_sem();
+                console_lock();
 
         console_locked = 1;
         console_may_schedule = 0;
         for_each_console(c)
                 if ((c->flags & CON_ENABLED) && c->unblank)
                         c->unblank();
-        release_console_sem();
+        console_unlock();
 }
 
 /*
@@ -1189,7 +1197,7 @@ struct tty_driver *console_device(int *index)
         struct console *c;
         struct tty_driver *driver = NULL;
 
-        acquire_console_sem();
+        console_lock();
         for_each_console(c) {
                 if (!c->device)
                         continue;
@@ -1197,7 +1205,7 @@ struct tty_driver *console_device(int *index)
                 if (driver)
                         break;
         }
-        release_console_sem();
+        console_unlock();
         return driver;
 }
 
@@ -1208,17 +1216,17 @@ struct tty_driver *console_device(int *index)
  */
 void console_stop(struct console *console)
 {
-        acquire_console_sem();
+        console_lock();
         console->flags &= ~CON_ENABLED;
-        release_console_sem();
+        console_unlock();
 }
 EXPORT_SYMBOL(console_stop);
 
 void console_start(struct console *console)
 {
-        acquire_console_sem();
+        console_lock();
         console->flags |= CON_ENABLED;
-        release_console_sem();
+        console_unlock();
 }
 EXPORT_SYMBOL(console_start);
 
@@ -1340,7 +1348,7 @@ void register_console(struct console *newcon)
          *      Put this console in the list - keep the
          *      preferred driver at the head of the list.
          */
-        acquire_console_sem();
+        console_lock();
         if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) {
                 newcon->next = console_drivers;
                 console_drivers = newcon;
@@ -1352,14 +1360,14 @@ void register_console(struct console *newcon)
         }
         if (newcon->flags & CON_PRINTBUFFER) {
                 /*
-                 * release_console_sem() will print out the buffered messages
+                 * console_unlock(); will print out the buffered messages
                  * for us.
                  */
                 spin_lock_irqsave(&logbuf_lock, flags);
                 con_start = log_start;
                 spin_unlock_irqrestore(&logbuf_lock, flags);
         }
-        release_console_sem();
+        console_unlock();
         console_sysfs_notify();
 
         /*
@@ -1396,7 +1404,7 @@ int unregister_console(struct console *console)
                 return braille_unregister_console(console);
 #endif
 
-        acquire_console_sem();
+        console_lock();
         if (console_drivers == console) {
                 console_drivers=console->next;
                 res = 0;
@@ -1418,7 +1426,7 @@ int unregister_console(struct console *console)
         if (console_drivers != NULL && console->flags & CON_CONSDEV)
                 console_drivers->flags |= CON_CONSDEV;
 
-        release_console_sem();
+        console_unlock();
         console_sysfs_notify();
         return res;
 }
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index ddabb54bb5c8..3c7cbc2c33be 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -215,7 +215,6 @@ void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter)
         put_pid(waiter->deadlock_task_pid);
         TRACE_WARN_ON(!plist_node_empty(&waiter->list_entry));
         TRACE_WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
-        TRACE_WARN_ON(waiter->task);
         memset(waiter, 0x22, sizeof(*waiter));
 }
 
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index a9604815786a..ab449117aaf2 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -20,41 +20,34 @@
 /*
  * lock->owner state tracking:
  *
- * lock->owner holds the task_struct pointer of the owner. Bit 0 and 1
- * are used to keep track of the "owner is pending" and "lock has
- * waiters" state.
+ * lock->owner holds the task_struct pointer of the owner. Bit 0
+ * is used to keep track of the "lock has waiters" state.
  *
- * owner        bit1    bit0
- * NULL         0       0       lock is free (fast acquire possible)
- * NULL         0       1       invalid state
- * NULL         1       0       Transitional State*
- * NULL         1       1       invalid state
- * taskpointer  0       0       lock is held (fast release possible)
- * taskpointer  0       1       task is pending owner
- * taskpointer  1       0       lock is held and has waiters
- * taskpointer  1       1       task is pending owner and lock has more waiters
- *
- * Pending ownership is assigned to the top (highest priority)
- * waiter of the lock, when the lock is released. The thread is woken
- * up and can now take the lock. Until the lock is taken (bit 0
- * cleared) a competing higher priority thread can steal the lock
- * which puts the woken up thread back on the waiters list.
+ * owner        bit0
+ * NULL         0       lock is free (fast acquire possible)
+ * NULL         1       lock is free and has waiters and the top waiter
+ *                              is going to take the lock*
+ * taskpointer  0       lock is held (fast release possible)
+ * taskpointer  1       lock is held and has waiters**
  *
  * The fast atomic compare exchange based acquire and release is only
- * possible when bit 0 and 1 of lock->owner are 0.
+ * possible when bit 0 of lock->owner is 0.
+ *
+ * (*) It also can be a transitional state when grabbing the lock
+ * with ->wait_lock is held. To prevent any fast path cmpxchg to the lock,
+ * we need to set the bit0 before looking at the lock, and the owner may be
+ * NULL in this small time, hence this can be a transitional state.
  *
- * (*) There's a small time where the owner can be NULL and the
- * "lock has waiters" bit is set.  This can happen when grabbing the lock.
- * To prevent a cmpxchg of the owner releasing the lock, we need to set this
- * bit before looking at the lock, hence the reason this is a transitional
- * state.
+ * (**) There is a small time when bit 0 is set but there are no
+ * waiters. This can happen when grabbing the lock in the slow path.
+ * To prevent a cmpxchg of the owner releasing the lock, we need to
+ * set this bit before looking at the lock.
  */
 
 static void
-rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner,
-                   unsigned long mask)
+rt_mutex_set_owner(struct rt_mutex *lock, struct task_struct *owner)
 {
-        unsigned long val = (unsigned long)owner | mask;
+        unsigned long val = (unsigned long)owner;
 
         if (rt_mutex_has_waiters(lock))
                 val |= RT_MUTEX_HAS_WAITERS;
@@ -203,15 +196,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
          * reached or the state of the chain has changed while we
          * dropped the locks.
          */
-        if (!waiter || !waiter->task)
+        if (!waiter)
                 goto out_unlock_pi;
 
         /*
          * Check the orig_waiter state. After we dropped the locks,
-         * the previous owner of the lock might have released the lock
-         * and made us the pending owner:
+         * the previous owner of the lock might have released the lock.
          */
-        if (orig_waiter && !orig_waiter->task)
+        if (orig_waiter && !rt_mutex_owner(orig_lock))
                 goto out_unlock_pi;
 
         /*
@@ -254,6 +246,17 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 
         /* Release the task */
         raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+        if (!rt_mutex_owner(lock)) {
+                /*
+                 * If the requeue above changed the top waiter, then we need
+                 * to wake the new top waiter up to try to get the lock.
+                 */
+
+                if (top_waiter != rt_mutex_top_waiter(lock))
+                        wake_up_process(rt_mutex_top_waiter(lock)->task);
+                raw_spin_unlock(&lock->wait_lock);
+                goto out_put_task;
+        }
         put_task_struct(task);
 
         /* Grab the next task */
@@ -296,78 +299,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 }
 
 /*
- * Optimization: check if we can steal the lock from the
- * assigned pending owner [which might not have taken the
- * lock yet]:
- */
-static inline int try_to_steal_lock(struct rt_mutex *lock,
-                                    struct task_struct *task)
-{
-        struct task_struct *pendowner = rt_mutex_owner(lock);
-        struct rt_mutex_waiter *next;
-        unsigned long flags;
-
-        if (!rt_mutex_owner_pending(lock))
-                return 0;
-
-        if (pendowner == task)
-                return 1;
-
-        raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-        if (task->prio >= pendowner->prio) {
-                raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-                return 0;
-        }
-
-        /*
-         * Check if a waiter is enqueued on the pending owners
-         * pi_waiters list. Remove it and readjust pending owners
-         * priority.
-         */
-        if (likely(!rt_mutex_has_waiters(lock))) {
-                raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-                return 1;
-        }
-
-        /* No chain handling, pending owner is not blocked on anything: */
-        next = rt_mutex_top_waiter(lock);
-        plist_del(&next->pi_list_entry, &pendowner->pi_waiters);
-        __rt_mutex_adjust_prio(pendowner);
-        raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
-        /*
-         * We are going to steal the lock and a waiter was
-         * enqueued on the pending owners pi_waiters queue. So
-         * we have to enqueue this waiter into
-         * task->pi_waiters list. This covers the case,
-         * where task is boosted because it holds another
-         * lock and gets unboosted because the booster is
-         * interrupted, so we would delay a waiter with higher
-         * priority as task->normal_prio.
-         *
-         * Note: in the rare case of a SCHED_OTHER task changing
-         * its priority and thus stealing the lock, next->task
-         * might be task:
-         */
-        if (likely(next->task != task)) {
-                raw_spin_lock_irqsave(&task->pi_lock, flags);
-                plist_add(&next->pi_list_entry, &task->pi_waiters);
-                __rt_mutex_adjust_prio(task);
-                raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-        }
-        return 1;
-}
-
-/*
  * Try to take an rt-mutex
  *
- * This fails
- * - when the lock has a real owner
- * - when a different pending owner exists and has higher priority than current
- *
  * Must be called with lock->wait_lock held.
+ *
+ * @lock:   the lock to be acquired.
+ * @task:   the task which wants to acquire the lock
+ * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock)
+static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+                struct rt_mutex_waiter *waiter)
 {
         /*
          * We have to be careful here if the atomic speedups are
@@ -390,15 +331,52 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock)
          */
         mark_rt_mutex_waiters(lock);
 
-        if (rt_mutex_owner(lock) && !try_to_steal_lock(lock, current))
+        if (rt_mutex_owner(lock))
                 return 0;
 
+        /*
+         * It will get the lock because of one of these conditions:
+         * 1) there is no waiter
+         * 2) higher priority than waiters
+         * 3) it is top waiter
+         */
+        if (rt_mutex_has_waiters(lock)) {
+                if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
+                        if (!waiter || waiter != rt_mutex_top_waiter(lock))
+                                return 0;
+                }
+        }
+
+        if (waiter || rt_mutex_has_waiters(lock)) {
+                unsigned long flags;
+                struct rt_mutex_waiter *top;
+
+                raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+                /* remove the queued waiter. */
+                if (waiter) {
+                        plist_del(&waiter->list_entry, &lock->wait_list);
+                        task->pi_blocked_on = NULL;
+                }
+
+                /*
+                 * We have to enqueue the top waiter(if it exists) into
+                 * task->pi_waiters list.
+                 */
+                if (rt_mutex_has_waiters(lock)) {
+                        top = rt_mutex_top_waiter(lock);
+                        top->pi_list_entry.prio = top->list_entry.prio;
+                        plist_add(&top->pi_list_entry, &task->pi_waiters);
+                }
+                raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+        }
+
         /* We got the lock. */
         debug_rt_mutex_lock(lock);
 
-        rt_mutex_set_owner(lock, current, 0);
+        rt_mutex_set_owner(lock, task);
 
-        rt_mutex_deadlock_account_lock(lock, current);
+        rt_mutex_deadlock_account_lock(lock, task);
 
         return 1;
 }
@@ -436,6 +414,9 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 
         raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
+        if (!owner)
+                return 0;
+
         if (waiter == rt_mutex_top_waiter(lock)) {
                 raw_spin_lock_irqsave(&owner->pi_lock, flags);
                 plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
@@ -472,21 +453,18 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 /*
  * Wake up the next waiter on the lock.
  *
- * Remove the top waiter from the current tasks waiter list and from
- * the lock waiter list. Set it as pending owner. Then wake it up.
+ * Remove the top waiter from the current tasks waiter list and wake it up.
  *
  * Called with lock->wait_lock held.
  */
 static void wakeup_next_waiter(struct rt_mutex *lock)
 {
         struct rt_mutex_waiter *waiter;
-        struct task_struct *pendowner;
         unsigned long flags;
 
         raw_spin_lock_irqsave(&current->pi_lock, flags);
 
         waiter = rt_mutex_top_waiter(lock);
-        plist_del(&waiter->list_entry, &lock->wait_list);
 
         /*
          * Remove it from current->pi_waiters. We do not adjust a
@@ -495,43 +473,19 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
          * lock->wait_lock.
          */
         plist_del(&waiter->pi_list_entry, &current->pi_waiters);
-        pendowner = waiter->task;
-        waiter->task = NULL;
 
-        rt_mutex_set_owner(lock, pendowner, RT_MUTEX_OWNER_PENDING);
+        rt_mutex_set_owner(lock, NULL);
 
         raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-        /*
-         * Clear the pi_blocked_on variable and enqueue a possible
-         * waiter into the pi_waiters list of the pending owner. This
-         * prevents that in case the pending owner gets unboosted a
-         * waiter with higher priority than pending-owner->normal_prio
-         * is blocked on the unboosted (pending) owner.
-         */
-        raw_spin_lock_irqsave(&pendowner->pi_lock, flags);
-
-        WARN_ON(!pendowner->pi_blocked_on);
-        WARN_ON(pendowner->pi_blocked_on != waiter);
-        WARN_ON(pendowner->pi_blocked_on->lock != lock);
-
-        pendowner->pi_blocked_on = NULL;
-
-        if (rt_mutex_has_waiters(lock)) {
-                struct rt_mutex_waiter *next;
-
-                next = rt_mutex_top_waiter(lock);
-                plist_add(&next->pi_list_entry, &pendowner->pi_waiters);
-        }
-        raw_spin_unlock_irqrestore(&pendowner->pi_lock, flags);
-
-        wake_up_process(pendowner);
+        wake_up_process(waiter->task);
 }
 
 /*
- * Remove a waiter from a lock
+ * Remove a waiter from a lock and give up
  *
- * Must be called with lock->wait_lock held
+ * Must be called with lock->wait_lock held and
+ * have just failed to try_to_take_rt_mutex().
  */
 static void remove_waiter(struct rt_mutex *lock,
                           struct rt_mutex_waiter *waiter)
@@ -543,11 +497,13 @@ static void remove_waiter(struct rt_mutex *lock,
 
         raw_spin_lock_irqsave(&current->pi_lock, flags);
         plist_del(&waiter->list_entry, &lock->wait_list);
-        waiter->task = NULL;
         current->pi_blocked_on = NULL;
         raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-        if (first && owner != current) {
+        if (!owner)
+                return;
+
+        if (first) {
 
                 raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
@@ -614,21 +570,19 @@ void rt_mutex_adjust_pi(struct task_struct *task)
  *                       or TASK_UNINTERRUPTIBLE)
  * @timeout:             the pre-initialized and started timer, or NULL for none
  * @waiter:              the pre-initialized rt_mutex_waiter
- * @detect_deadlock:     passed to task_blocks_on_rt_mutex
  *
  * lock->wait_lock must be held by the caller.
  */
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
                     struct hrtimer_sleeper *timeout,
-                    struct rt_mutex_waiter *waiter,
-                    int detect_deadlock)
+                    struct rt_mutex_waiter *waiter)
 {
         int ret = 0;
 
         for (;;) {
                 /* Try to acquire the lock: */
-                if (try_to_take_rt_mutex(lock))
+                if (try_to_take_rt_mutex(lock, current, waiter))
                         break;
 
                 /*
@@ -645,39 +599,11 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
                                 break;
                 }
 
-                /*
-                 * waiter->task is NULL the first time we come here and
-                 * when we have been woken up by the previous owner
-                 * but the lock got stolen by a higher prio task.
-                 */
-                if (!waiter->task) {
-                        ret = task_blocks_on_rt_mutex(lock, waiter, current,
-                                                      detect_deadlock);
-                        /*
-                         * If we got woken up by the owner then start loop
-                         * all over without going into schedule to try
-                         * to get the lock now:
-                         */
-                        if (unlikely(!waiter->task)) {
-                                /*
-                                 * Reset the return value. We might
-                                 * have returned with -EDEADLK and the
-                                 * owner released the lock while we
-                                 * were walking the pi chain.
-                                 */
-                                ret = 0;
-                                continue;
-                        }
-                        if (unlikely(ret))
-                                break;
-                }
-
                 raw_spin_unlock(&lock->wait_lock);
 
                 debug_rt_mutex_print_deadlock(waiter);
 
-                if (waiter->task)
-                        schedule_rt_mutex(lock);
+                schedule_rt_mutex(lock);
 
                 raw_spin_lock(&lock->wait_lock);
                 set_current_state(state);
@@ -698,12 +624,11 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
         int ret = 0;
 
         debug_rt_mutex_init_waiter(&waiter);
-        waiter.task = NULL;
 
         raw_spin_lock(&lock->wait_lock);
 
         /* Try to acquire the lock again: */
-        if (try_to_take_rt_mutex(lock)) {
+        if (try_to_take_rt_mutex(lock, current, NULL)) {
                 raw_spin_unlock(&lock->wait_lock);
                 return 0;
         }
@@ -717,12 +642,14 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
                         timeout->task = NULL;
         }
 
-        ret = __rt_mutex_slowlock(lock, state, timeout, &waiter,
-                                  detect_deadlock);
+        ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+
+        if (likely(!ret))
+                ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
 
         set_current_state(TASK_RUNNING);
 
-        if (unlikely(waiter.task))
+        if (unlikely(ret))
                 remove_waiter(lock, &waiter);
 
         /*
@@ -737,14 +664,6 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
         if (unlikely(timeout))
                 hrtimer_cancel(&timeout->timer);
 
-        /*
-         * Readjust priority, when we did not get the lock. We might
-         * have been the pending owner and boosted. Since we did not
-         * take the lock, the PI boost has to go.
-         */
-        if (unlikely(ret))
-                rt_mutex_adjust_prio(current);
-
         debug_rt_mutex_free_waiter(&waiter);
 
         return ret;
@@ -762,7 +681,7 @@ rt_mutex_slowtrylock(struct rt_mutex *lock)
 
         if (likely(rt_mutex_owner(lock) != current)) {
 
-                ret = try_to_take_rt_mutex(lock);
+                ret = try_to_take_rt_mutex(lock, current, NULL);
                 /*
                  * try_to_take_rt_mutex() sets the lock waiters
                  * bit unconditionally. Clean this up.
@@ -992,7 +911,7 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 {
         __rt_mutex_init(lock, NULL);
         debug_rt_mutex_proxy_lock(lock, proxy_owner);
-        rt_mutex_set_owner(lock, proxy_owner, 0);
+        rt_mutex_set_owner(lock, proxy_owner);
         rt_mutex_deadlock_account_lock(lock, proxy_owner);
 }
 
@@ -1008,7 +927,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
                            struct task_struct *proxy_owner)
 {
         debug_rt_mutex_proxy_unlock(lock);
-        rt_mutex_set_owner(lock, NULL, 0);
+        rt_mutex_set_owner(lock, NULL);
         rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
@@ -1034,20 +953,14 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 
         raw_spin_lock(&lock->wait_lock);
 
-        mark_rt_mutex_waiters(lock);
-
-        if (!rt_mutex_owner(lock) || try_to_steal_lock(lock, task)) {
-                /* We got the lock for task. */
-                debug_rt_mutex_lock(lock);
-                rt_mutex_set_owner(lock, task, 0);
+        if (try_to_take_rt_mutex(lock, task, NULL)) {
                 raw_spin_unlock(&lock->wait_lock);
-                rt_mutex_deadlock_account_lock(lock, task);
                 return 1;
         }
 
         ret = task_blocks_on_rt_mutex(lock, waiter, task, detect_deadlock);
 
-        if (ret && !waiter->task) {
+        if (ret && !rt_mutex_owner(lock)) {
                 /*
                  * Reset the return value. We might have
                  * returned with -EDEADLK and the owner
@@ -1056,6 +969,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
                  */
                 ret = 0;
         }
+
+        if (unlikely(ret))
+                remove_waiter(lock, waiter);
+
         raw_spin_unlock(&lock->wait_lock);
 
         debug_rt_mutex_print_deadlock(waiter);
@@ -1110,12 +1027,11 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
         set_current_state(TASK_INTERRUPTIBLE);
 
-        ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter,
-                                  detect_deadlock);
+        ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
 
         set_current_state(TASK_RUNNING);
 
-        if (unlikely(waiter->task))
+        if (unlikely(ret))
                 remove_waiter(lock, waiter);
 
         /*
@@ -1126,13 +1042,5 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 
         raw_spin_unlock(&lock->wait_lock);
 
-        /*
-         * Readjust priority, when we did not get the lock. We might have been
-         * the pending owner and boosted. Since we did not take the lock, the
-         * PI boost has to go.
-         */
-        if (unlikely(ret))
-                rt_mutex_adjust_prio(current);
-
         return ret;
 }
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index 97a2f81866af..53a66c85261b 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -91,9 +91,8 @@ task_top_pi_waiter(struct task_struct *p)
 /*
  * lock->owner state tracking:
  */
-#define RT_MUTEX_OWNER_PENDING  1UL
-#define RT_MUTEX_HAS_WAITERS    2UL
-#define RT_MUTEX_OWNER_MASKALL  3UL
+#define RT_MUTEX_HAS_WAITERS    1UL
+#define RT_MUTEX_OWNER_MASKALL  1UL
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 {
@@ -101,17 +100,6 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
                 ((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
 }
 
-static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock)
-{
-        return (struct task_struct *)
-                ((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
-}
-
-static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
-{
-        return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
-}
-
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 77e9166d7bbf..354769979c02 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -699,7 +699,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
         cfs_rq->nr_running--;
 }
 
-#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
+#ifdef CONFIG_FAIR_GROUP_SCHED
+# ifdef CONFIG_SMP
 static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq,
                                             int global_update)
 {
@@ -762,6 +763,51 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
                 list_del_leaf_cfs_rq(cfs_rq);
 }
 
+static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
+                                long weight_delta)
+{
+        long load_weight, load, shares;
+
+        load = cfs_rq->load.weight + weight_delta;
+
+        load_weight = atomic_read(&tg->load_weight);
+        load_weight -= cfs_rq->load_contribution;
+        load_weight += load;
+
+        shares = (tg->shares * load);
+        if (load_weight)
+                shares /= load_weight;
+
+        if (shares < MIN_SHARES)
+                shares = MIN_SHARES;
+        if (shares > tg->shares)
+                shares = tg->shares;
+
+        return shares;
+}
+
+static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+        if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
+                update_cfs_load(cfs_rq, 0);
+                update_cfs_shares(cfs_rq, 0);
+        }
+}
+# else /* CONFIG_SMP */
+static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
+{
+}
+
+static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg,
+                                long weight_delta)
+{
+        return tg->shares;
+}
+
+static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
+{
+}
+# endif /* CONFIG_SMP */
 static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
                             unsigned long weight)
 {
@@ -782,7 +828,7 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 {
         struct task_group *tg;
         struct sched_entity *se;
-        long load_weight, load, shares;
+        long shares;
 
         if (!cfs_rq)
                 return;
@@ -791,32 +837,14 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
         se = tg->se[cpu_of(rq_of(cfs_rq))];
         if (!se)
                 return;
-
-        load = cfs_rq->load.weight + weight_delta;
-
-        load_weight = atomic_read(&tg->load_weight);
-        load_weight -= cfs_rq->load_contribution;
-        load_weight += load;
-
-        shares = (tg->shares * load);
-        if (load_weight)
-                shares /= load_weight;
-
-        if (shares < MIN_SHARES)
-                shares = MIN_SHARES;
-        if (shares > tg->shares)
-                shares = tg->shares;
+#ifndef CONFIG_SMP
+        if (likely(se->load.weight == tg->shares))
+                return;
+#endif
+        shares = calc_cfs_shares(cfs_rq, tg, weight_delta);
 
         reweight_entity(cfs_rq_of(se), se, shares);
 }
-
-static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
-{
-        if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
-                update_cfs_load(cfs_rq, 0);
-                update_cfs_shares(cfs_rq, 0);
-        }
-}
 #else /* CONFIG_FAIR_GROUP_SCHED */
 static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 {
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index bc86bb32e126..0f1bd83db985 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -170,7 +170,8 @@ static int proc_taint(struct ctl_table *table, int write,
 #endif
 
 #ifdef CONFIG_MAGIC_SYSRQ
-static int __sysrq_enabled; /* Note: sysrq code ises it's own private copy */
+/* Note: sysrq code uses it's own private copy */
+static int __sysrq_enabled = SYSRQ_DEFAULT_ENABLE;
 
 static int sysrq_sysctl_handler(ctl_table *table, int write,
                                 void __user *buffer, size_t *lenp,
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3e216e01bbd1..c55ea2433471 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -642,8 +642,7 @@ static void tick_nohz_switch_to_nohz(void)
         }
         local_irq_enable();
 
-        printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n",
-               smp_processor_id());
+        printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n", smp_processor_id());
 }
 
 /*
@@ -795,8 +794,10 @@ void tick_setup_sched_timer(void)
         }
 
 #ifdef CONFIG_NO_HZ
-        if (tick_nohz_enabled)
+        if (tick_nohz_enabled) {
                 ts->nohz_mode = NOHZ_MODE_HIGHRES;
+                printk(KERN_INFO "Switched to NOHz mode on CPU #%d\n", smp_processor_id());
+        }
 #endif
 }
 #endif /* HIGH_RES_TIMERS */